AI Model Leaderboard
Models ranked by BenchLM overall score. Click a row for score, rank, creator, and nearby models.
50 of 24,924 tracked entries · snapshot 2026-09-21 · type to filter, click a header to sort
| Rank | Model | Score | Creator | Source | |
|---|---|---|---|---|---|
| 1 |  Claude Fable 5.1 | 84.74 | Anthropic |  benchlm-models | |
| 2 |  GPT-6 Astra | 82.81 | OpenAI | benchlm-models | |
| 3 | Claude Opus 5 | 81.87 | Anthropic | benchlm-models | |
| 4 | Claude Fable 5 | 81.41 | Anthropic | benchlm-models | |
| 5 | GPT-5.6 Sol | 80.46 | OpenAI | benchlm-models | |
| 6 |  Gemini 3.8 Flash | 75.89 | benchlm-models | ||
| 7 |  Kimi K3 | 74.43 | Moonshot AI | benchlm-models | |
| 8 |  Qwen3.8 Max | 73.17 | Alibaba | benchlm-models | |
| 9 | Claude Opus 4.8 | 72.17 | Anthropic | benchlm-models | |
| 10 | GPT-5.5 | 71.86 | OpenAI | benchlm-models | |
| 11 | GPT-5.4 | 70.88 | OpenAI | benchlm-models | |
| 12 | Claude Opus 4.7 | 70.60 | Anthropic | benchlm-models | |
| 13 | Gemini 3.1 Pro | 70.14 | benchlm-models | ||
| 14 |  Grok 4.6 | 69.74 | xAI | benchlm-models | |
| 15 | Claude Sonnet 5 | 69.68 | Anthropic | benchlm-models | |
| 16 | Claude Opus 4.6 | 69.21 | Anthropic | benchlm-models | |
| 17 | Gemini 3.7 Flash | 68.52 | benchlm-models | ||
| 18 | Gemini 3.6 Flash | 68.42 | benchlm-models | ||
| 19 | Gemini 3.5 Flash | 68.02 | benchlm-models | ||
| 20 | Grok 4.5 | 67.99 | xAI | benchlm-models | |
| 21 | Grok 4.20 | 67.27 | xAI | benchlm-models | |
| 22 |  GLM-5.3 | 66.93 | Z.AI | benchlm-models | |
| 23 | Qwen3.7 Max | 66.87 | Alibaba | benchlm-models | |
| 24 | GLM-5.2 | 66.68 | Z.AI | benchlm-models | |
| 25 | Gemini 3 Pro | 66.36 | benchlm-models | ||
| 26 | Kimi K2.7 Code | 65.60 | Moonshot AI | benchlm-models | |
| 27 | Kimi K2.6 | 65.50 | Moonshot AI | benchlm-models | |
| 28 |  Ornith-1.5-397B | 65.32 | Ornith AI | benchlm-models | |
| 29 | GPT-5.2 | 64.86 | OpenAI | benchlm-models | |
| 30 | Qwen3.8-27B | 64.29 | Alibaba | benchlm-models | |
| 31 |  dots3-note Preview | 64.14 | Dots Studio | benchlm-models | |
| 32 | GPT-5.3 Codex | 64.03 | OpenAI | benchlm-models | |
| 33 | Qwen 3.6 Max | 63.94 | Alibaba | benchlm-models | |
| 34 |  DeepSeek V4 Pro 0813 | 63.69 | DeepSeek | benchlm-models | |
| 35 | GLM-5.1 | 63.26 | Z.AI | benchlm-models | |
| 36 | GPT-5.1 | 63.18 | OpenAI | benchlm-models | |
| 37 | Claude Sonnet 4.6 | 62.86 | Anthropic | benchlm-models | |
| 38 |  MiMo-V2-Pro | 62.51 | Xiaomi | benchlm-models | |
| 39 | Gemini 3 Flash | 61.94 | benchlm-models | ||
| 40 | Qwen3.7 Plus | 61.60 | Alibaba | benchlm-models | |
| 41 | GLM-5 | 61.47 | Z.AI | benchlm-models | |
| 42 |  MiniMax M3 | 61.25 | MiniMax | benchlm-models | |
| 43 |  Hy4 preview | 60.89 | Tencent | benchlm-models | |
| 44 | Hy3 | 60.79 | Tencent | benchlm-models | |
| 45 |  Inkling | 60.38 | Thinking Machines Lab | benchlm-models | |
| 46 | Qwen3.6 Plus | 60.36 | Alibaba | benchlm-models | |
| 47 | Grok 4.3 | 59.73 | xAI | benchlm-models | |
| 48 | Gemini 3.5 Flash-Lite | 58.78 | benchlm-models | ||
| 49 | Claude Opus 4.5 | 58.42 | Anthropic | benchlm-models | |
| 50 | Grok 4.1 | 57.99 | xAI | benchlm-models |
No entries match. Clear the filter above to see all 50.